Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    This neuron detects numeric literal tokens (decimal numbers) in source code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    เกอร
    -0.07
     eyebrows
    -0.07
     tham
    -0.06
    (Notification
    -0.06
     histogram
    -0.06
    ك
    -0.06
     Training
    -0.06
    prop
    -0.06
     Consequently
    -0.06
    \Resources
    -0.06
    POSITIVE LOGITS
     چرا
    0.07
     niệm
    0.06
     ISPs
    0.06
     asker
    0.06
    _poll
    0.06
     grö
    0.06
    }${
    0.06
     arp
    0.06
     surrounds
    0.06
    histoire
    0.06
    Act Density 0.032%

    No Known Activations